What AI does, and what it costs
Seven tasks, each with a fixed price in credits and a per-call money cap.
Detection never uses AI. Everything a model does here happens after a deterministic rule has already found something, and only when a person asks for it.
| Task | Credits | What it does |
|---|---|---|
| Classify a signal | Free | Sorts a detection into a bucket. The cheap model has never lost this one. |
| Explain a finding | 4 | Describes the finding in your application’s terms, not in the abstract. |
| Authorization analysis | 6 | Judges who is allowed to call a route, from the code. |
| Fix with AI | 7 | A plan for the change, written against your file. |
| Fix as a patch | 18 | The file rewritten and opened as a draft pull request. |
| Critical escalation | 20 | A second, better model re-judges anything critical before you see it. |
| Deep review | 23 | The whole application judged at once, on the premium tier. |
For scale: a deep review of a site costs a few dozen credits, and Pro includes 1,000 per usage window. Scanning the live site itself costs no credits on paid plans.
Questions
Does AI decide what counts as a vulnerability?
No. Detection is deterministic and repeatable, with a rule id on every finding. AI explains, judges authorization, and writes fixes - always after the fact, always on request.
Which models do you use?
A cheap tier, a default tier and a premium tier, chosen per task by what the task actually needs. The provider sits behind an adapter, so the choice can change without changing what you see.
Is my code used to train models?
No. Nothing you connect is used to train anything, and nothing is retained for another customer’s benefit.
Something here wrong, missing or out of date? Tell us and we will fix the page.